© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 84296
    Prev
    Next
    INDEX
    Explanations

    oise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebHost
    -0.08
    ינטרנט
    -0.07
    ('../../
    -0.07
     weeks
    -0.07
     nettsteder
    -0.07
    nist
    -0.06
    HB
    -0.06
    <Props
    -0.06
    [@"
    -0.06
     ו
    -0.06
    POSITIVE LOGITS
    .return
    0.08
    ]()↵
    0.07
    装甲
    0.07
    -ap
    0.07
    $is
    0.07
    post
    0.07
    .ce
    0.07
     bloc
    0.07
    的话语
    0.07
     ageing
    0.07
    Activations Density 0.001%

    No Known Activations